Free llms.txt Generator

What is an llms.txt file

llms.txt is a markdown file at the root of a website, proposed at llmstxt.org, that gives language models a short map of the site. The format is fixed:

• An H1 with the site or product name. This is the only required part.
• A blockquote with a one-line summary.
• Optional paragraphs with more context.
• H2 sections, each with a list of links written as - [Page name](url): notes.
• A section named Optional for links an AI tool can skip when it needs a shorter context.

# Acme

> Acme turns meetings into searchable notes for product teams.

## Docs

- [Getting started](https://acme.com/docs/getting-started): Install Acme and record your first meeting
- [API reference](https://acme.com/docs/api): Endpoints for notes and transcripts

## Product

- [Pricing](https://acme.com/pricing): Free, Pro and Business plans

## Optional

- [Privacy policy](https://acme.com/privacy)

How this llms.txt generator builds your file

The generator follows fixed rules. No AI writes or rewrites your text:

• Name and summary. The H1 comes from your homepage's og:site_name or title, and the summary from its meta description.
• Pages. We read the sitemap named in robots.txt, or /sitemap.xml, including up to three child sitemaps of a sitemap index. Without a sitemap, we use the links on your homepage.
• Filtering. We leave out other domains, URLs with query parameters, sign-in and checkout pages, tag and author archives, pagination, feeds, translated copies, pages robots.txt blocks, broken pages and pages marked noindex. Every page we leave out is listed with the reason.
• Sections. Pages are grouped by URL path into Docs, Product, Use cases, Blog and Company, with legal pages under Optional. Up to 30 pages are listed: top-level pages first, a few pages from each folder, and the six newest blog posts.
• Descriptions. Each link's note is that page's own meta description. Pages without one get a plain link for you to describe.

Already have an llms.txt file? The llms.txt checker validates its format and tests its links.

Treat the result as a first draft. The best llms.txt files are short and point to the pages that answer real questions about your product.

Where to upload llms.txt

The file must load at https://your-domain.com/llms.txt as plain text. A copy in a subfolder, such as /docs/llms.txt, covers only that folder.

Next.js, Astro, Vite and most static sites

Put llms.txt in the public folder and deploy. Files there are served from the site root.

WordPress

Upload the file to the folder that holds wp-config.php over SFTP or your host's file manager. Some SEO plugins can also generate and serve llms.txt.

Webflow, Framer and other hosted builders

Some hosted builders do not let you add files at the root. Check your builder's settings or help center for llms.txt or root file support. If there is none, serve the file from a CDN in front of the site, as below.

Cloudflare and other CDNs

If your site runs behind a CDN with edge functions, such as Cloudflare Workers, you can return the file for the /llms.txt path from there.

Does llms.txt help AI visibility?

No one has shown that it does. llms.txt is a community proposal. As of October 2026, none of the major AI companies has said its crawlers use llms.txt to choose which pages to cite. It is cheap to publish and can help AI coding tools and agents that look for it, so it is worth a few minutes, but it is not a ranking lever.

llms.txt also does not control access. Crawlers that respect robots.txt follow robots.txt, so that is where you allow or block GPTBot, ClaudeBot and other AI crawlers. To see what those crawlers can actually reach and read on your site, run the AI visibility checker.

If you build an AI tool, an Ordalin listing is free and gives AI answers another researched page about your product to cite.

FAQ